Partial discharge diagnosis method based on improved ANFIS

A diagnostic method and partial discharge technology, applied in the field of GIS insulation detection, can solve problems such as classification and identification

Pending Publication Date: 2022-08-05
STATE GRID CORP OF CHINA +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current partial discharge identification method cannot effectively classify and identify different discharge modes.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Partial discharge diagnosis method based on improved ANFIS
  • Partial discharge diagnosis method based on improved ANFIS
  • Partial discharge diagnosis method based on improved ANFIS

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] A partial discharge diagnosis method based on improved ANFIS, firstly, using the grid division method to initialize the before and after parameters according to the dimension of the training samples and the number and type of membership functions, and then deduce the fuzzy inference rules, and then use the sample data for training. The hybrid algorithm of the propagation method and the least square method is used to obtain the structural parameters of the identification system. The sample data obtained by the experiment needs to be processed in a series of processes to obtain the specific pattern recognition results, such as figure 1 (2) wavelet denoising; (3) pulse extraction; (4) calculation of statistical distribution; (5) extraction of characteristic parameters; (6) reduction of characteristic parameters of PCA algorithm dimensional processing; (7) training samples are used to train ANFIS, and test samples are used to verify ANFIS performance; (8) output recognition ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a partial discharge diagnosis method based on an improved ANFIS, and relates to the technical field of GIS insulation detection, and the method comprises the steps: firstly, employing a grid division method to initialize parameters before and after the initialization according to the dimensions of a training sample and the number and type of membership functions, deducing a fuzzy inference rule, and then carrying out the training through employing sample data, according to the method, a mixed algorithm of a back propagation method and a least square method is adopted, then structure parameters of a recognition system are obtained, sample data obtained through experiments need to be subjected to a series of processing to obtain a specific pattern recognition result, and classification and recognition can be effectively carried out through the method provided by the invention; and the ANFIS combines the advantages of the neural network and the fuzzy reasoning logic and is the combination and improvement of the neural network and the fuzzy reasoning logic.

Description

technical field [0001] The invention relates to the technical field of GIS insulation detection, in particular to a partial discharge diagnosis method based on improved ANFIS. Background technique [0002] In order to detect the insulation status of gas-insulated switchgear (GIS), an effective method is partial discharge detection. Since different GIS defect modes have different discharge characteristics, the application of PD detection methods should not only be able to collect PD pulses, but also be able to identify defect types. However, the discharge data characteristics of various GIS defect modes in practical applications are different. In addition to the correct identification of discharge pulses, the application of PD detection also includes the interpretation of various PD signals to effectively identify the type of defect. [0003] At present, the common PD identification methods include support vector machine (SVM), neural network, fuzzy logic method, etc. Among...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G06N5/04G01R31/327G01R31/12
CPCG06N3/084G06N5/048G01R31/3275G01R31/1254G06N3/043G06F2218/06G06F2218/08G06F2218/12G06F18/2135G06F18/214Y02E30/30
Inventor 赵廷志冯新岩毛琨孙佑飞张海杰卢志海崔勇王晓亮张明兴李承振王文森刘晗史伟波薛帅丁晶陈健石璐杜滨洋
Owner STATE GRID CORP OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap